Open PhD position (4 years, fully funded) in Information Retrieval at TU Delft

Multimedia Information Retrieval Lab at Delft University of Technology,
the Netherlands, offers a PhD position funded by the European Union in
the project "PuppyIR - Information Retrieval for Children".

Project Summary

PuppyIR (a new project funded by the EU 7th Framework) will provide an
open suite of components that can be used by system designers to tailor
IR systems for the specific needs of children. Current Information
Retrieval (IR) systems are designed for adults: they return information
that is unsuitable for children, present information in lists that
children find difficult to manage and make it difficult for children to
ask for information. PuppyIR will develop new interaction paradigms that
allow children to express their information needs simply and have
results presented in an intuitive way. It will develop Information
Services that can summarise content for children, moderate information
for children, help children safely build social networks and
intelligently aggregate for presentation to children.

More information about the project and its participants can be found at:
http://nirict.3tu.nl/nirict-projects/puppy-ir.doc/
More information about Multimedia Information Retrieval Lab:
http://ict.ewi.tudelft.nl/index.php?option=com_sections&id=45&Itemid=109

Role in Project

The PhD student in Delft studies the retrieval models and their
implementation to support the interfaces and interaction styles
specialized for children's behaviour when accessing information online
(developed by other project participants). The student contributes
solutions in the areas of multimodal presentation technology, text and
multimedia content mining, and natural language processing of children's
texts. Specifically, the Delft contribution concentrates on a query
assistance module based on entity retrieval and expert finding
approaches, social network analysis, and, moderated discovery of
information guided by opinion detection. Research prototypes are made to
extend and exploit the PuppyIR open source framework. The PhD student
also participates in the tasks to identify what evaluation measures make
sense for evaluation of search tools for children, and contributes to
the development of test collections for the system-oriented evaluation
of search algorithms for children.

Requirements for the PhD student

* Degree in Computer Science, Artificial Intelligence, Computational
Linguistics or Cognitive Science
* Strong technical background in Machine Learning and/or Information
Retrieval
* Excellent programming skills
* Good command of the English language
* Sincere interest in learning about how to adapt search technologies to
the cognitive abilities of children

Appointment and Salary

The full-time appointment is temporary for four years. The starting
salary is ˆ 2042 gross per month increasing to a maximum of ˆ 2612 gross
per month in the fourth year. Moreover, an 8% bonus share (holiday
supplement) and an end-of-year bonus of 8.3% is provided annually, as
well as excellent secondary benefits. The preferable starting date is
1st September 2009.

How to apply

Applications should be sent by e-mail and include the following
documents (in English):
* Curriculum Vitae (incl. publication list and a statement of research
qualifications)
* copy of university degree
* copy of transcript listing all university marks
* a cover letter explaining the motivation for doing research in IR,
with details of research interests/experience, background, programming
skills and the knowledge of data mining/retrieval technologies
* two letters of reference

Applications should be sent to Pavel Serdyukov (p.serdyukov AT tudelft
DOT nl) and Prof.dr.ir. Arjen P. de Vries (arjen.de.vries AT cwi DOT
nl). In the ideal case, those candidates that will be around Boston, US,
from 18 to 25 July (during the SIGIR conference), might be interviewed
immediately. Please, specify if that is possible in your application.